Right. But ... this would limit you to either extremely small models or extremely large FPGA's, yes? If there's a simple machine learning task that requires a sub microsecond latency I can see the point but otherwise??
Ahhh, so is this a chip "more optimised" for connecting GPU's to reality ... or are they skipping the GPU step entirely? Are GPU's only for training now?
I reboot a lot. Mostly I want to know that should the system need to reboot for whatever reason, that it will all come back up again. I run a very lightly loaded site and I highly doubt anybody notices the minute (or so) loss of service caused by rebooting.
There was a brief fascination with user mode TCP over DPDK (or similar). What happened with that? Can you get similar performance with QUIC? Does io_uring make it all a moot point?
Thing is, I have stopped expecting Xcode to be any good.
Actual native macOS/iOS development got beaten senseless when the App Store made it clear that "unsustainably low" was the expected price point for third party developers; and that Apple were treating the store more or less as a market research exercise and good ideas absolutely would be stolen.
So it's an internal tool, really. And we're I-guess-lucky that they document it and release it for the proles.